1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
#!/usr/bin/env python
import numpy as np
import quikr
import os
import sys
import gzip
from subprocess import *
import platform
import argparse
def main():
"""
You can call this script independently, and will save the
trained matrix as a numpy file.
example: python quikr-train.py -i input.fasta -k 6 -o trained_matrix.npy
"""
parser = argparse.ArgumentParser(description=
" quikr_train returns a custom trained matrix that can be used with \
the quikr function. \n You must supply a kmer. \n ")
parser.add_argument("-i", "--input", help="training database of sequences (fasta format)", required=True)
parser.add_argument("-o", "--output", help="sensing matrix (text file)", required=True)
parser.add_argument("-k", "--kmer", help="kmer size (integer)",
type=int, required=False )
parser.add_argument("-z", "--compress", help="compress output (flag)",
action='store_true', required=False)
args = parser.parse_args()
if not os.path.isfile(args.input):
parser.error( "Input database not found")
# call the quikr train function, save the output with np.save
matrix = quikr.train_matrix(args.input, args.kmer)
if args.kmer is None:
kmer = 6
else:
kmer = args.kmer
if args.compress:
output_file = gzip.open(args.output, "wb")
else:
output_file = open(args.output, "wb")
np.save(output_file, matrix)
return 0
if __name__ == "__main__":
sys.exit(main())
|
